Raffaele Ferrara at Odigo looks into how automated encounters are becoming ever more prevalent in the customer journey in industries such as retail and banking.
Efforts to integrate human intelligence into automated systems, through using natural language processing (NLP), and specifically natural language understanding (NLU), aim to deliver an enhanced customer experience.
Let’s say it’s the Christmas season, and your contact centre’s agents are likely steeling themselves for a number of potential customer interactions: the frantic, incoherent parent who’s missing part of a gift for their children; the frazzled and scatterbrained project manager who needs to check on store hours yet again; the homeowner troubleshooting their wi-fi connection so they can hook up the new PS5 on Christmas morning.
Some issues require more specialised insight than others, and customers can be subject to unnecessarily long waiting times. For contact centre agents to handle every interaction makes for a very inefficient contact centre operation. That’s where artificial intelligence (AI) can play a role in optimising your agents’ workloads.
The Buying Public Is Increasingly Dependent on NLP-Led Interactions
The further into the future we go, the more prevalent automated encounters will be in the customer journey. 67% of consumers worldwide interacted with a chatbot to get customer support over the past 12 months.
Even though customers may prefer the warmth of human interaction, solutions such as omnichannel bots and AI-driven IVRs are becoming increasingly accepted by customers to resolve their simpler issues quickly.
The technology driving automated response systems is also marching forward, as efforts by tech leaders such as Google to integrate human intelligence into automated systems to deliver an enhanced customer experience develop.
AI innovations such as natural language processing algorithms handle free-form text-based language received during customer interactions from channels such as live chat and instant messaging.
In the retail industry, some organisations have even been testing out NLP in physical settings, as evidenced by the deployment of automated helpers at brick-and-mortar outlets. It excels by identifying contexts and patterns in speech and text to sort information more efficiently – in this case, customer queries.
NLU, a Subset of NLP That’s Made to Understand
Natural language understanding is a subset of natural language processing that is defined by what it extracts from unstructured text, which identifies nuance in language and derives hidden or abstract meanings from text or voice.
It is a technology that can lead to more efficient call qualification because instances can be trained to understand jargon from specific industries such as retail, banking, utilities, and more. For example, the meaning of a simple word like “premium” is context-specific depending on the nature of the business a customer is interacting with.
When a call does make its way to the agent, NLU can also assist them by suggesting the next best actions while the call is still ongoing.
The Real-Time Agent Assist tool aids in note-taking and data entry and uses information from ongoing conversations to do things like activating knowledge retrieval and behaviour guidance in real-time.
All of which works in the service of suggesting the next-best actions to satisfy customers and improve the customer experience.
How Contact Centres Use NLU for CX
Omnichannel bots can be extremely good at what they do if they are well fed with data. The more linguistic information an NLU-based solution onboards, the better a job it can do in assisting customers, such as in routing calls more effectively.
This is thanks to machine learning (ML), which is software that can learn from its past experiences — in this case, previous conversations with customers. When supervised, ML can be trained to effectively recognise meaning in speech, automatically extracting key information without the need for a human agent to handle conversations.
Thus, simple queries (like those about a store’s hours) can be taken care of quickly while agents tackle more serious problems, like troubleshooting an internet connection. All of which helps improve the customer experience, and makes your contact centre more efficient.
An automated system should approach the customer with politeness and familiarity with their issues, especially if the caller is a repeat one. It’s a customer service best practice, after all, to be able to get to the root of their issue quickly, and showing that extra knowledge and care is the cherry on top.
It’s important to not over-optimise the human traits of these bots, however, at the risk of alienating customers. Thanks to the uncanny valley effect, interactions with machines can become very discomfiting.
Put simply, bots should be programmed to mirror human traits without making painstaking attempts to emulate them. After all, they’re taking care of routine queries, freeing up time for the agents so they can focus on tasks where their skills are truly needed. The point is not to replace agents entirely.
Call Centre Helper is not responsible for the content of these guest blog posts. The opinions expressed in this article are those of the author, and do not necessarily reflect those of Call Centre Helper.